ondrej-merkun/skill-audit

Scan AI agent skills (Claude Code, Cursor, Copilot, Codex, Gemini, Windsurf, Cline) for prompt injection and malicious code.

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Activelast commit May 12, 2026
License
None

Pinned Snippet

workflow.ymlSHA-pinned
uses: ondrej-merkun/skill-audit@836d3e00ed562834380e5d799a771de2aa57be0d # v0.2.1

tags can be moved; commit SHAs can't. why a SHA?

namedescriptionrequireddefault
version@ondrej-merkun/skill-audit npm package version to run (e.g. "0.2.1" or "latest")nolatest
pathWorking directory to scan (default: repo root)no.
argsAdditional arguments passed verbatim to `skill-audit scan`no""
fail-onExit 1 when any result meets this verdict band or worse. One of: review, failnofail
agentRestrict discovery to one agent id (claude-code, cursor, copilot, cross-agent). Leave blank for all agents.no""
upload-resultsUpload JSON results as a workflow artifactnotrue
results-filePath where the JSON results file is writtennoskill-audit-results.json
namedescription
results-filePath to the JSON results file
verdictWorst verdict across all scanned skills (PASS, REVIEW, FAIL)